© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 143610
    Prev
    Next
    INDEX
    Explanations

    US company interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    0.77
    ir
    0.77
    ina
    0.75
    it
    0.68
     क्षेत्र
    0.67
    ita
    0.66
    "]:
    0.66
    iven
    0.65
     Pham
    0.64
    ine
    0.64
    POSITIVE LOGITS
    ты
    0.67
    ку
    0.64
    ⓵
    0.64
    кі
    0.61
    British
    0.60
    𝗷
    0.59
     photons
    0.59
    벍
    0.57
    чатку
    0.57
    станти
    0.57
    Activations Density 0.018%

    No Known Activations